Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment

TL;DR

This paper introduces a deep neural network model for image quality assessment that works in both no-reference and full-reference settings, learning local and global quality metrics without handcrafted features.

Contribution

The proposed deep neural network architecture is novel in its ability to perform both NR and FR IQA and to jointly learn local quality and importance weights in a unified framework.

Findings

Outperforms state-of-the-art IQA methods on multiple databases.

Demonstrates high generalization ability across different datasets.

Achieves superior accuracy in both no-reference and full-reference scenarios.

Abstract

We present a deep neural network-based approach to image quality assessment (IQA). The network is trained end-to-end and comprises ten convolutional layers and five pooling layers for feature extraction, and two fully connected layers for regression, which makes it significantly deeper than related IQA models. Unique features of the proposed architecture are that: 1) with slight adaptations it can be used in a no-reference (NR) as well as in a full-reference (FR) IQA setting and 2) it allows for joint learning of local quality and local weights, i.e., relative importance of local quality to the global quality estimate, in an unified framework. Our approach is purely data-driven and does not rely on hand-crafted features or other types of prior domain knowledge about the human visual system or image statistics. We evaluate the proposed approach on the LIVE, CISQ, and TID2013 databases as well as the LIVE In the wild image quality challenge database and show superior performance to state-of-the-art NR and FR IQA methods. Finally, cross-database evaluation shows a high ability to generalize between different databases, indicating a high robustness of the learned features.